942 lines
37 KiB
Plaintext
942 lines
37 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
" <script type=\"text/javascript\">\n",
|
||
" window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
|
||
" if (window.MathJax && window.MathJax.Hub && window.MathJax.Hub.Config) {window.MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
|
||
" if (typeof require !== 'undefined') {\n",
|
||
" require.undef(\"plotly\");\n",
|
||
" requirejs.config({\n",
|
||
" paths: {\n",
|
||
" 'plotly': ['https://cdn.plot.ly/plotly-2.12.1.min']\n",
|
||
" }\n",
|
||
" });\n",
|
||
" require(['plotly'], function(Plotly) {\n",
|
||
" window._Plotly = Plotly;\n",
|
||
" });\n",
|
||
" }\n",
|
||
" </script>\n",
|
||
" "
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"import requests\n",
|
||
"import json\n",
|
||
"\n",
|
||
"from datetime import datetime,timedelta\n",
|
||
"\n",
|
||
"# 变量定义\n",
|
||
"login_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n",
|
||
"search_url = \"http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos\"\n",
|
||
"queryDataListItemNos_url = \"http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryDataListItemNos\"\n",
|
||
"\n",
|
||
"\n",
|
||
"login_push_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n",
|
||
"upload_url = \"http://10.200.32.39/jingbo-api/api/dw/dataValue/pushDataValueList\"\n",
|
||
"\n",
|
||
"login_data = {\n",
|
||
" \"data\": {\n",
|
||
" \"account\": \"api_dev\",\n",
|
||
" \"password\": \"ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=\",\n",
|
||
" \"tenantHashCode\": \"8a4577dbd919675758d57999a1e891fe\",\n",
|
||
" \"terminal\": \"API\"\n",
|
||
" },\n",
|
||
" \"funcModule\": \"API\",\n",
|
||
" \"funcOperation\": \"获取token\"\n",
|
||
"}\n",
|
||
"\n",
|
||
"login_push_data = {\n",
|
||
" \"data\": {\n",
|
||
" \"account\": \"api_dev\",\n",
|
||
" \"password\": \"ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=\",\n",
|
||
" \"tenantHashCode\": \"8a4577dbd919675758d57999a1e891fe\",\n",
|
||
" \"terminal\": \"API\"\n",
|
||
" },\n",
|
||
" \"funcModule\": \"API\",\n",
|
||
" \"funcOperation\": \"获取token\"\n",
|
||
"}\n",
|
||
"\n",
|
||
"read_file_path_name = \"液化气数据.xlsx\"\n",
|
||
"one_cols = []\n",
|
||
"two_cols = []\n",
|
||
"\n",
|
||
"import pandas as pd\n",
|
||
"import numpy as np\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import seaborn as sn\n",
|
||
"import random\n",
|
||
"import time\n",
|
||
"\n",
|
||
"from plotly import __version__\n",
|
||
"from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot\n",
|
||
"\n",
|
||
"from sklearn import preprocessing\n",
|
||
"\n",
|
||
"from pandas import Series,DataFrame\n",
|
||
"\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"\n",
|
||
"import sklearn.datasets as datasets\n",
|
||
"\n",
|
||
"#导入机器学习算法模型\n",
|
||
"from sklearn.linear_model import Lasso\n",
|
||
"from xgboost import XGBRegressor\n",
|
||
"\n",
|
||
"import statsmodels.api as sm\n",
|
||
"try:\n",
|
||
" from keras.preprocessing.sequence import TimeseriesGenerator\n",
|
||
"except:\n",
|
||
" from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator\n",
|
||
"\n",
|
||
"import plotly.express as px\n",
|
||
"import plotly.graph_objects as go\n",
|
||
"\n",
|
||
"import xgboost as xgb\n",
|
||
"from xgboost import plot_importance, plot_tree\n",
|
||
"from sklearn.metrics import mean_absolute_error\n",
|
||
"from statsmodels.tools.eval_measures import mse,rmse\n",
|
||
"from sklearn.model_selection import GridSearchCV\n",
|
||
"from xgboost import XGBRegressor\n",
|
||
"import warnings\n",
|
||
"import pickle\n",
|
||
"\n",
|
||
"from sklearn.metrics import mean_squared_error\n",
|
||
"\n",
|
||
"#切割训练数据和样本数据\n",
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"\n",
|
||
"#用于模型评分\n",
|
||
"from sklearn.metrics import r2_score\n",
|
||
"\n",
|
||
"le = preprocessing.LabelEncoder()\n",
|
||
"\n",
|
||
"# print(__version__) # requires version >= 1.9.0\n",
|
||
"\n",
|
||
"\n",
|
||
"import cufflinks as cf\n",
|
||
"cf.go_offline()\n",
|
||
"\n",
|
||
"random.seed(100)\n",
|
||
"\n",
|
||
"%matplotlib inline\n",
|
||
"\n",
|
||
"# 数据获取\n",
|
||
"\n",
|
||
"def get_head_auth():\n",
|
||
" login_res = requests.post(url=login_url, json=login_data, timeout=(3, 5))\n",
|
||
" text = json.loads(login_res.text)\n",
|
||
" if text[\"status\"]:\n",
|
||
" token = text[\"data\"][\"accessToken\"]\n",
|
||
" print('获取的token:',token)\n",
|
||
" return token\n",
|
||
" else:\n",
|
||
" print(\"获取认证失败\")\n",
|
||
" return None\n",
|
||
"\n",
|
||
"\n",
|
||
"def get_data_value(token, dataItemNoList,date):\n",
|
||
" search_data = {\n",
|
||
" \"data\": {\n",
|
||
" \"date\": date,\n",
|
||
" \"dataItemNoList\": dataItemNoList\n",
|
||
" },\n",
|
||
" \"funcModule\": \"数据项\",\n",
|
||
" \"funcOperation\": \"查询\"\n",
|
||
" }\n",
|
||
" \n",
|
||
" \n",
|
||
" headers = {\"Authorization\": token}\n",
|
||
" search_res = requests.post(url=search_url, headers=headers, json=search_data, timeout=(3, 5))\n",
|
||
" print('数据项查询参数search_data：')\n",
|
||
" print(search_data)\n",
|
||
" print('数据项查询结果search_res：')\n",
|
||
" print(search_res.text)\n",
|
||
" \n",
|
||
" try:\n",
|
||
" search_value = json.loads(search_res.text)[\"data\"]\n",
|
||
" \n",
|
||
" print(\"数据项查询结果:\", search_value)\n",
|
||
" except json.JSONDecodeError as e:\n",
|
||
" print(f\"Error decoding JSON: {e}\")\n",
|
||
" print(\"Response content:\", search_res.text)\n",
|
||
" return None \n",
|
||
" if search_value:\n",
|
||
" return search_value\n",
|
||
" else:\n",
|
||
" print(\"今天没有新数据\")\n",
|
||
" return search_value\n",
|
||
"\n",
|
||
"\n",
|
||
"def get_head_push_auth():\n",
|
||
" login_res = requests.post(url=login_push_url, json=login_push_data, timeout=(3, 5))\n",
|
||
" text = json.loads(login_res.text)\n",
|
||
" if text[\"status\"]:\n",
|
||
" token = text[\"data\"][\"accessToken\"]\n",
|
||
" return token\n",
|
||
" else:\n",
|
||
" print(\"获取认证失败\")\n",
|
||
" return None\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"def upload_data_to_system(token_push,date):\n",
|
||
" data = {\n",
|
||
" \"funcModule\": \"数据表信息列表\",\n",
|
||
" \"funcOperation\": \"新增\",\n",
|
||
" \"data\": [\n",
|
||
" {\"dataItemNo\": \"250855713|Forecast_Price|ACN\",\n",
|
||
" \"dataDate\": date,\n",
|
||
" \"dataStatus\": \"add\",\n",
|
||
" \"dataValue\": forecast_price()\n",
|
||
" }\n",
|
||
"\n",
|
||
" ]\n",
|
||
" }\n",
|
||
" # headers = {\"Authorization\": token_push}\n",
|
||
" # res = requests.post(url=upload_url, headers=headers, json=data, timeout=(3, 5))\n",
|
||
" # print(res.text)\n",
|
||
" print('预测值：',data['data'][0]['dataValue'])\n",
|
||
"\n",
|
||
" \n",
|
||
"# def upload_data_to_system(token):\n",
|
||
"# data = {\n",
|
||
"# \"funcModule\": \"数据表信息列表\",\n",
|
||
"# \"funcOperation\": \"新增\",\n",
|
||
"# \"data\": [\n",
|
||
"# {\"dataItemNo\": \"C01100036|Forecast_ Price|ACN\",\n",
|
||
"# \"dataDate\": '20230706',\n",
|
||
"# \"dataStatus\": \"add\",\n",
|
||
"# \"dataValue\": 3780.0\n",
|
||
"# }\n",
|
||
"\n",
|
||
"# ]\n",
|
||
"# }\n",
|
||
"# headers = {\"Authorization\": token}\n",
|
||
"# res = requests.post(url=upload_url, headers=headers, json=data, timeout=(3, 5))\n",
|
||
"# print(res.text)\n",
|
||
"\n",
|
||
"price_list = []\n",
|
||
" \n",
|
||
"def forecast_price():\n",
|
||
" # df_test = pd.read_csv('定价模型数据收集0212.csv')\n",
|
||
" df_test = pd.read_excel('液化气数据.xlsx')\n",
|
||
" df_test.drop([0],inplace=True)\n",
|
||
" try:\n",
|
||
" df_test['Date']=pd.to_datetime(df_test['Date'], format='%m/%d/%Y',infer_datetime_format=True)\n",
|
||
" except:\n",
|
||
" df_test['Date']=pd.to_datetime(df_test['Date'], format=r'%Y-%m-%d',infer_datetime_format=True)\n",
|
||
"\n",
|
||
"\n",
|
||
" df_test_1 = df_test\n",
|
||
" df_test_1=df_test_1.fillna(df_test.ffill())\n",
|
||
" df_test_1=df_test_1.fillna(df_test_1.bfill())\n",
|
||
"\n",
|
||
" # 选择用于模型训练的列名称\n",
|
||
" col_for_training = df_test_1.columns\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
" import joblib\n",
|
||
" Best_model_DalyLGPrice = joblib.load(\"日度价格预测_液化气最佳模型.pkl\")\n",
|
||
" # 最新的一天为最后一行的数据\n",
|
||
" \n",
|
||
" df_test_1_Day = df_test_1.tail(1)\n",
|
||
" # 移除不需要的列\n",
|
||
" df_test_1_Day.index = df_test_1_Day[\"Date\"]\n",
|
||
" df_test_1_Day = df_test_1_Day.drop([\"Date\"], axis= 1)\n",
|
||
" df_test_1_Day=df_test_1_Day.drop('Price',axis=1)\n",
|
||
" df_test_1_Day=df_test_1_Day.dropna()\n",
|
||
"\n",
|
||
" for col in df_test_1_Day.columns:\n",
|
||
" df_test_1_Day[col] = pd.to_numeric(df_test_1_Day[col],errors='coerce')\n",
|
||
" #预测今日价格，显示至小数点后两位\n",
|
||
" Ypredict_Today=Best_model_DalyLGPrice.predict(df_test_1_Day)\n",
|
||
"\n",
|
||
" df_test_1_Day['日度预测价格']=Ypredict_Today\n",
|
||
" print(df_test_1_Day['日度预测价格'])\n",
|
||
" a = df_test_1_Day['日度预测价格']\n",
|
||
" a = a[0]\n",
|
||
" a = float(a)\n",
|
||
" a = round(a,2)\n",
|
||
" price_list.append(a)\n",
|
||
" return a\n",
|
||
"def optimize_Model():\n",
|
||
" from sklearn.model_selection import train_test_split\n",
|
||
" from sklearn.impute import SimpleImputer\n",
|
||
" from sklearn.preprocessing import OrdinalEncoder\n",
|
||
" from sklearn.feature_selection import SelectFromModel\n",
|
||
" from sklearn.metrics import mean_squared_error, r2_score\n",
|
||
" import pandas as pd\n",
|
||
"\n",
|
||
" pd.set_option('display.max_rows',40) \n",
|
||
" pd.set_option('display.max_columns',40) \n",
|
||
" df_test = pd.read_excel('液化气数据.xlsx')\n",
|
||
" df_test.drop([0],inplace=True)\n",
|
||
" try:\n",
|
||
" df_test['Date']=pd.to_datetime(df_test['Date'], format='%m/%d/%Y',infer_datetime_format=True)\n",
|
||
" except:\n",
|
||
" df_test['Date']=pd.to_datetime(df_test['Date'], format=r'%Y-%m-%d',infer_datetime_format=True)\n",
|
||
"\n",
|
||
" \n",
|
||
" #将缺失值补为前一个或者后一个数值\n",
|
||
" df_test_1 = df_test\n",
|
||
" df_test_1=df_test_1.fillna(df_test.ffill())\n",
|
||
" df_test_1=df_test_1.fillna(df_test_1.bfill())\n",
|
||
" df_test_1[\"Date\"] = pd.to_datetime(df_test_1[\"Date\"])\n",
|
||
" df_test_1.index = df_test_1[\"Date\"]\n",
|
||
" df_test_1 = df_test_1.drop([\"Date\"], axis= 1)\n",
|
||
" df_test_1 = df_test_1.astype('float')\n",
|
||
" \n",
|
||
" \n",
|
||
" import numpy as np\n",
|
||
" import pandas as pd\n",
|
||
" from pandas import Series,DataFrame\n",
|
||
"\n",
|
||
" import matplotlib.pyplot as plt\n",
|
||
"\n",
|
||
" import sklearn.datasets as datasets\n",
|
||
"\n",
|
||
" #导入机器学习算法模型\n",
|
||
" from sklearn.linear_model import Lasso\n",
|
||
" from xgboost import XGBRegressor\n",
|
||
"\n",
|
||
" import statsmodels.api as sm\n",
|
||
" try:\n",
|
||
" from keras.preprocessing.sequence import TimeseriesGenerator\n",
|
||
" except:\n",
|
||
" from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator\n",
|
||
"\n",
|
||
" import plotly.express as px\n",
|
||
" import plotly.graph_objects as go\n",
|
||
"\n",
|
||
" import xgboost as xgb\n",
|
||
" from xgboost import plot_importance, plot_tree\n",
|
||
" from sklearn.metrics import mean_absolute_error\n",
|
||
" from statsmodels.tools.eval_measures import mse,rmse\n",
|
||
" from sklearn.model_selection import GridSearchCV\n",
|
||
" from xgboost import XGBRegressor\n",
|
||
" import warnings\n",
|
||
" import pickle\n",
|
||
"\n",
|
||
" from sklearn.metrics import mean_squared_error\n",
|
||
"\n",
|
||
" #切割训练数据和样本数据\n",
|
||
" from sklearn.model_selection import train_test_split\n",
|
||
"\n",
|
||
" #用于模型评分\n",
|
||
" from sklearn.metrics import r2_score\n",
|
||
"\n",
|
||
" dataset1=df_test_1.drop('Price',axis=1)#.astype(float)\n",
|
||
"\n",
|
||
" y=df_test_1['Price']\n",
|
||
"\n",
|
||
" x=dataset1 \n",
|
||
"\n",
|
||
" train = x\n",
|
||
" target = y\n",
|
||
"\n",
|
||
" #切割数据样本集合测试集\n",
|
||
" X_train,x_test,y_train,y_true = train_test_split(train,target,test_size=0.2,random_state=0)\n",
|
||
"\n",
|
||
" #模型缩写\n",
|
||
" Lasso = Lasso(random_state=0)\n",
|
||
" XGBR = XGBRegressor(random_state=0)\n",
|
||
" #训练模型\n",
|
||
" Lasso.fit(X_train,y_train)\n",
|
||
" XGBR.fit(X_train,y_train)\n",
|
||
" #模型拟合\n",
|
||
" y_pre_Lasso = Lasso.predict(x_test)\n",
|
||
" y_pre_XGBR = XGBR.predict(x_test)\n",
|
||
"\n",
|
||
" #计算Lasso、XGBR、RandomForestR、AdaBoostR、GradientBoostingR、BaggingRegressor各模型的R²\n",
|
||
" Lasso_score = r2_score(y_true,y_pre_Lasso)\n",
|
||
" XGBR_score=r2_score(y_true,y_pre_XGBR)\n",
|
||
"\n",
|
||
" #计算Lasso、XGBR的MSE和RMSE\n",
|
||
" Lasso_MSE=mean_squared_error(y_true, y_pre_Lasso)\n",
|
||
" XGBR_MSE=mean_squared_error(y_true, y_pre_XGBR)\n",
|
||
"\n",
|
||
" Lasso_RMSE=np.sqrt(Lasso_MSE)\n",
|
||
" XGBR_RMSE=np.sqrt(XGBR_MSE)\n",
|
||
" # 将不同模型的不同误差值整合成一个表格\n",
|
||
" model_results = pd.DataFrame([['Lasso', Lasso_RMSE, Lasso_score],\n",
|
||
" ['XgBoost', XGBR_RMSE, XGBR_score]],\n",
|
||
" columns = ['模型(Model)','均方根误差(RMSE)', 'R^2 score'])\n",
|
||
" #将模型名称(Model)列设置为索引\n",
|
||
" model_results1=model_results.set_index('模型(Model)')\n",
|
||
"\n",
|
||
" model_results1\n",
|
||
" #定义plot_feature_importance函数，该函数用于计算特征重要性。此部分代码无需调整\n",
|
||
" def plot_feature_importance(importance,names,model_type):\n",
|
||
" feature_importance = np.array(importance)\n",
|
||
" feature_names = np.array(names)\n",
|
||
"\n",
|
||
" data={'feature_names':feature_names,'feature_importance':feature_importance}\n",
|
||
" fi_df = pd.DataFrame(data)\n",
|
||
"\n",
|
||
" fi_df.sort_values(by=['feature_importance'], ascending=False,inplace=True)\n",
|
||
"\n",
|
||
" plt.figure(figsize=(10,8))\n",
|
||
" sn.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'])\n",
|
||
"\n",
|
||
" plt.title(model_type + \" \"+'FEATURE IMPORTANCE')\n",
|
||
" plt.xlabel('FEATURE IMPORTANCE')\n",
|
||
" plt.ylabel('FEATURE NAMES')\n",
|
||
" from pylab import mpl\n",
|
||
" %pylab\n",
|
||
" mpl.rcParams['font.sans-serif'] = ['SimHei']\n",
|
||
" ## Xgboost 模型参数优化-初步\n",
|
||
" #参考: https://juejin.im/post/6844903661013827598 \n",
|
||
" #每次调参时，备选参数数值以同数量级的1、3、10设置即可（比如设置1、3、10，或0.1、0.3、1.0，或0.01,0.03,0.10即可）\n",
|
||
"\n",
|
||
" from xgboost import XGBRegressor\n",
|
||
" from sklearn.model_selection import GridSearchCV\n",
|
||
"\n",
|
||
" estimator = XGBRegressor(random_state=0,\n",
|
||
" nthread=4,\n",
|
||
" seed=0\n",
|
||
" )\n",
|
||
" parameters = {\n",
|
||
" 'max_depth': range (2, 11, 2), # 树的最大深度\n",
|
||
" 'n_estimators': range (50, 101, 10), # 迭代次数\n",
|
||
" 'learning_rate': [0.01, 0.03, 0.1, 0.3, 0.5, 1]\n",
|
||
" }\n",
|
||
"\n",
|
||
" grid_search_XGB = GridSearchCV(\n",
|
||
" estimator=estimator,\n",
|
||
" param_grid=parameters,\n",
|
||
" # n_jobs = 10,\n",
|
||
" cv = 3,\n",
|
||
" verbose=True\n",
|
||
" )\n",
|
||
"\n",
|
||
" grid_search_XGB.fit(X_train, y_train)\n",
|
||
" #如果电脑在此步骤报错，可能是因为计算量太大，超过硬件可支持程度，可注释掉“n_jobs=10”一行\n",
|
||
"\n",
|
||
" best_parameters = grid_search_XGB.best_estimator_.get_params()\n",
|
||
" y_pred = grid_search_XGB.predict(x_test)\n",
|
||
"\n",
|
||
" op_XGBR_score = r2_score(y_true,y_pred)\n",
|
||
" op_XGBR_MSE= mean_squared_error(y_true, y_pred)\n",
|
||
" op_XGBR_RMSE= np.sqrt(op_XGBR_MSE)\n",
|
||
"\n",
|
||
" model_results2 = pd.DataFrame([['Optimized_Xgboost', op_XGBR_RMSE, op_XGBR_score]],\n",
|
||
" columns = ['模型(Model)', '均方根误差(RMSE)', 'R^2 score'])\n",
|
||
" model_results2=model_results2.set_index('模型(Model)')\n",
|
||
"\n",
|
||
" try:\n",
|
||
" results = model_results1.append(model_results2, ignore_index = False)\n",
|
||
" except:\n",
|
||
" results = pd.concat([model_results1,model_results2],ignore_index=True)\n",
|
||
" import pickle\n",
|
||
"\n",
|
||
" Pkl_Filename = \"日度价格预测_液化气最佳模型.pkl\" \n",
|
||
"\n",
|
||
" with open(Pkl_Filename, 'wb') as file: \n",
|
||
" pickle.dump(grid_search_XGB, file)\n",
|
||
"\n",
|
||
"def read_xls_data():\n",
|
||
" \"\"\"获取特征项ID\"\"\"\n",
|
||
" global one_cols, two_cols\n",
|
||
" # 使用pandas读取Excel文件\n",
|
||
" df = pd.read_excel(read_file_path_name, header=None) # 不自动识别列名\n",
|
||
" # 获取第二行数据（索引为1）\n",
|
||
" one_cols = df.iloc[1].tolist()[1:]\n",
|
||
" print(f'获取到的数据项ID{one_cols}')\n",
|
||
"\n",
|
||
"\n",
|
||
"def start(date=''):\n",
|
||
" \"\"\"获取当日数据\"\"\"\n",
|
||
" read_xls_data()\n",
|
||
" token = get_head_auth()\n",
|
||
" if not token:\n",
|
||
" return\n",
|
||
" \n",
|
||
" cur_time,cur_time2 = getNow(date)\n",
|
||
" print(f\"获取{cur_time}数据\")\n",
|
||
" datas = get_data_value(token, one_cols,date=cur_time)\n",
|
||
" if not datas:\n",
|
||
" return\n",
|
||
"\n",
|
||
" append_rows = [cur_time2]\n",
|
||
" dataItemNo_dataValue = {}\n",
|
||
" for data_value in datas:\n",
|
||
" if \"dataValue\" not in data_value:\n",
|
||
" print(data_value)\n",
|
||
" dataItemNo_dataValue[data_value[\"dataItemNo\"]] = \"\"\n",
|
||
" else:\n",
|
||
" dataItemNo_dataValue[data_value[\"dataItemNo\"]] = data_value[\"dataValue\"]\n",
|
||
" \n",
|
||
" for value in one_cols:\n",
|
||
" if value in dataItemNo_dataValue:\n",
|
||
" append_rows.append(dataItemNo_dataValue[value])\n",
|
||
" else:\n",
|
||
" append_rows.append(\"\")\n",
|
||
" print('添加的行：',append_rows)\n",
|
||
" save_xls_2(append_rows)\n",
|
||
"\n",
|
||
"\n",
|
||
"def getNow(date='', offset=0):\n",
|
||
" \"\"\"生成指定日期的两种格式字符串\n",
|
||
" Args:\n",
|
||
" date: 支持多种输入类型：\n",
|
||
" - datetime对象\n",
|
||
" - 字符串格式（支持'%Y-%m-%d'和'%Y%m%d'）\n",
|
||
" - 空字符串表示当前日期\n",
|
||
" offset: 日期偏移天数\n",
|
||
" Returns:\n",
|
||
" tuple: (紧凑日期字符串, 标准日期字符串)\n",
|
||
" \"\"\"\n",
|
||
" # 日期解析逻辑\n",
|
||
" if isinstance(date, datetime):\n",
|
||
" now = date\n",
|
||
" else:\n",
|
||
" now = datetime.now()\n",
|
||
" if date:\n",
|
||
" # 尝试多种日期格式解析\n",
|
||
" for fmt in ('%Y-%m-%d', '%Y%m%d', '%Y/%m/%d'):\n",
|
||
" try:\n",
|
||
" now = datetime.strptime(str(date), fmt)\n",
|
||
" break\n",
|
||
" except ValueError:\n",
|
||
" continue\n",
|
||
" else:\n",
|
||
" raise ValueError(f\"无法解析的日期格式: {date}\")\n",
|
||
"\n",
|
||
" # 应用日期偏移\n",
|
||
" now = now - timedelta(days=offset)\n",
|
||
" \n",
|
||
" # 统一格式化输出\n",
|
||
" date_str = now.strftime(\"%Y-%m-%d\")\n",
|
||
" compact_date = date_str.replace(\"-\", \"\")\n",
|
||
" return compact_date, date_str\n",
|
||
"\n",
|
||
"def start_1(date=''):\n",
|
||
" \"\"\"补充昨日数据\"\"\"\n",
|
||
" read_xls_data()\n",
|
||
" token = get_head_auth()\n",
|
||
" if not token:\n",
|
||
" return\n",
|
||
" \n",
|
||
" cur_time,cur_time2 = getNow(date,offset=1)\n",
|
||
" print(f\"补充{cur_time}数据\")\n",
|
||
" datas = get_data_value(token, one_cols,date=cur_time)\n",
|
||
" if not datas:\n",
|
||
" print(f\"{cur_time}没有数据\")\n",
|
||
" return\n",
|
||
"\n",
|
||
" append_rows = [cur_time2]\n",
|
||
" dataItemNo_dataValue = {}\n",
|
||
" for data_value in datas:\n",
|
||
" if \"dataValue\" not in data_value:\n",
|
||
" print(data_value)\n",
|
||
" dataItemNo_dataValue[data_value[\"dataItemNo\"]] = \"\"\n",
|
||
" else:\n",
|
||
" dataItemNo_dataValue[data_value[\"dataItemNo\"]] = data_value[\"dataValue\"]\n",
|
||
" \n",
|
||
" for value in one_cols:\n",
|
||
" if value in dataItemNo_dataValue:\n",
|
||
" append_rows.append(dataItemNo_dataValue[value])\n",
|
||
" else:\n",
|
||
" append_rows.append(\"\")\n",
|
||
" print('添加的行：',append_rows)\n",
|
||
" save_xls_2(append_rows)\n",
|
||
"\n",
|
||
"\n",
|
||
"def save_xls_2(append_rows):\n",
|
||
" \"\"\"保存或更新数据到Excel文件\n",
|
||
" 参数:\n",
|
||
" append_rows (list): 需要追加/更新的数据行，格式为[日期, 数据项1, 数据项2,...]\n",
|
||
" \"\"\"\n",
|
||
" try:\n",
|
||
" # 读取现有数据（假设第一行为列名）\n",
|
||
" df = pd.read_excel('液化气数据.xlsx', sheet_name=0)\n",
|
||
" # 转换append_rows为DataFrame\n",
|
||
" append_rows = pd.DataFrame([append_rows],columns=df.columns)\n",
|
||
" # 创建新数据行\n",
|
||
" new_date = append_rows['Date'].values[0]\n",
|
||
" \n",
|
||
" dates = df['Date'].to_list()\n",
|
||
" # 判断日期是否存在\n",
|
||
" if new_date in dates:\n",
|
||
" # 找到日期所在行的索引\n",
|
||
" date_mask = df['Date'] == new_date\n",
|
||
" # 存在则更新数据\n",
|
||
" df.loc[date_mask] = append_rows.values\n",
|
||
" print(f\"更新 {new_date} 数据\")\n",
|
||
" else:\n",
|
||
" # 不存在则追加数据\n",
|
||
" df = pd.concat([df, append_rows], ignore_index=True)\n",
|
||
" print(df.head())\n",
|
||
" print(df.tail())\n",
|
||
" print(f\"插入 {new_date} 新数据\")\n",
|
||
" \n",
|
||
" # 保存更新后的数据\n",
|
||
" df.to_excel('液化气数据.xlsx', index=False, engine='openpyxl')\n",
|
||
" \n",
|
||
" except FileNotFoundError:\n",
|
||
" # 如果文件不存在则创建新文件\n",
|
||
" pd.DataFrame([append_rows]).to_excel('液化气数据.xlsx', index=False, engine='openpyxl')\n",
|
||
" except Exception as e:\n",
|
||
" print(f\"保存数据时发生错误: {str(e)}\")\n",
|
||
"\n",
|
||
"def check_data(dataItemNo):\n",
|
||
" token = get_head_auth()\n",
|
||
" if not token:\n",
|
||
" return\n",
|
||
"\n",
|
||
" datas = get_data_value(token, dataItemNo)\n",
|
||
" if not datas:\n",
|
||
" return\n",
|
||
"\n",
|
||
"def get_queryDataListItemNos_value(token, url, dataItemNoList, dateStart, dateEnd):\n",
|
||
"\n",
|
||
" search_data = {\n",
|
||
" \"funcModule\": \"数据项\",\n",
|
||
" \"funcOperation\": \"查询\",\n",
|
||
" \"data\": {\n",
|
||
" \"dateStart\": dateStart,\n",
|
||
" \"dateEnd\": dateEnd,\n",
|
||
" \"dataItemNoList\": dataItemNoList # 数据项编码,代表 brent最低价和最高价\n",
|
||
" }\n",
|
||
" }\n",
|
||
"\n",
|
||
" headers = {\"Authorization\": token}\n",
|
||
" search_res = requests.post(url=url, headers=headers, json=search_data, timeout=(3, 5))\n",
|
||
" search_value = json.loads(search_res.text)[\"data\"]\n",
|
||
" if search_value:\n",
|
||
" return search_value\n",
|
||
" else:\n",
|
||
" return None\n",
|
||
"\n",
|
||
"def save_queryDataListItemNos_xls(data_df,dataItemNoList):\n",
|
||
" current_year_month = datetime.now().strftime('%Y-%m')\n",
|
||
" grouped = data_df.groupby(\"dataDate\")\n",
|
||
"\n",
|
||
" # 使用openpyxl打开xlsx文件\n",
|
||
" from openpyxl import load_workbook\n",
|
||
" workbook = load_workbook('液化气数据.xlsx')\n",
|
||
"\n",
|
||
" # 创建新工作簿\n",
|
||
" new_workbook = load_workbook('液化气数据.xlsx')\n",
|
||
" \n",
|
||
" for sheetname in workbook.sheetnames:\n",
|
||
" sheet = workbook[sheetname]\n",
|
||
" new_sheet = new_workbook[sheetname]\n",
|
||
" \n",
|
||
" current_year_month_row = 0\n",
|
||
" # 查找当前月份数据起始行\n",
|
||
" for row_idx, row in enumerate(sheet.iter_rows(values_only=True), 1):\n",
|
||
" if str(row[0]).startswith(current_year_month):\n",
|
||
" current_year_month_row += 1\n",
|
||
"\n",
|
||
" # 追加新数据\n",
|
||
" if sheetname == workbook.sheetnames[0]:\n",
|
||
" start_row = sheet.max_row - current_year_month_row + 1\n",
|
||
" for row_idx, (date, group) in enumerate(grouped, start=start_row):\n",
|
||
" new_sheet.cell(row=row_idx, column=1, value=date)\n",
|
||
" for j, dataItemNo in enumerate(dataItemNoList, start=2):\n",
|
||
" if group[group[\"dataItemNo\"] == dataItemNo][\"dataValue\"].values:\n",
|
||
" new_sheet.cell(row=row_idx, column=j, \n",
|
||
" value=group[group[\"dataItemNo\"] == dataItemNo][\"dataValue\"].values[0])\n",
|
||
"\n",
|
||
" # 保存修改后的xlsx文件\n",
|
||
" new_workbook.save(\"液化气数据.xlsx\")\n",
|
||
"\n",
|
||
"\n",
|
||
"def queryDataListItemNos(date=None,token=None):\n",
|
||
" df = pd.read_excel('液化气数据.xlsx')\n",
|
||
" dataItemNoList = df.iloc[0].tolist()[1:]\n",
|
||
" if token is None:\n",
|
||
" token = get_head_auth()\n",
|
||
" if not token:\n",
|
||
" print('token获取失败')\n",
|
||
" return\n",
|
||
" # 获取当前日期\n",
|
||
" if date is None:\n",
|
||
" current_date = datetime.now()\n",
|
||
" else:\n",
|
||
" current_date = date\n",
|
||
" # 获取当月1日\n",
|
||
" first_day_of_month = current_date.replace(day=1)\n",
|
||
" # 格式化为 YYYYMMDD 格式\n",
|
||
" dateEnd = current_date.strftime('%Y%m%d')\n",
|
||
" dateStart = first_day_of_month.strftime('%Y%m%d')\n",
|
||
" search_value = get_queryDataListItemNos_value(token, queryDataListItemNos_url, dataItemNoList, dateStart, dateEnd)\n",
|
||
" data_df = pd.DataFrame(search_value)\n",
|
||
" data_df[\"dataDate\"] = pd.to_datetime(data_df[\"dataDate\"])\n",
|
||
" data_df[\"dataDate\"] = data_df[\"dataDate\"].dt.strftime('%Y-%m-%d')\n",
|
||
" save_queryDataListItemNos_xls(data_df,dataItemNoList)\n",
|
||
" print('当月数据更新完成')\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"def main(start_date=None,token=None,token_push=None):\n",
|
||
" if start_date is None:\n",
|
||
" start_date = datetime.now()\n",
|
||
" if token is None:\n",
|
||
" token = get_head_auth()\n",
|
||
" if token_push is None:\n",
|
||
" token_push = get_head_push_auth()\n",
|
||
" date = start_date.strftime('%Y%m%d')\n",
|
||
" print(date)\n",
|
||
" # 更新当月数据\n",
|
||
" queryDataListItemNos(start_date,token)\n",
|
||
" # 更新当日数据\n",
|
||
" # start(date)\n",
|
||
" # 训练模型\n",
|
||
" optimize_Model()\n",
|
||
" # 预测&上传预测结果\n",
|
||
" upload_data_to_system(token_push,start_date)\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"\n",
|
||
"# if __name__ == \"__main__\":\n",
|
||
"# print('运行中')\n",
|
||
"# # 需要单独运行放开\n",
|
||
"# # start()\n",
|
||
"# # start_1(date='2025-01-22')\n",
|
||
"# # start_1()\n",
|
||
"\n",
|
||
"# # 每天定时12点运行\n",
|
||
"# while True:\n",
|
||
"# try:\n",
|
||
"# # 获取当前时间\n",
|
||
"# current_time = time.strftime(\"%H:%M:%S\", time.localtime())\n",
|
||
"# current_time_1 = time.strftime(\"%H:%M:%S\", time.localtime())\n",
|
||
"# # print(current_time_1)\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"# # 判断当前时间是否为执行任务的时间点\n",
|
||
"# if current_time == \"09:15:00\":\n",
|
||
"# print(\"执行定时任务\")\n",
|
||
" # start()\n",
|
||
"\n",
|
||
"# # 休眠1秒钟，避免过多占用CPU资源\n",
|
||
"# time.sleep(1)\n",
|
||
"\n",
|
||
"# elif current_time_1 == \"20:00:00\":\n",
|
||
"# print(\"更新数据\")\n",
|
||
"# start_1()\n",
|
||
"# time.sleep(1)\n",
|
||
"# except:\n",
|
||
"# print('执行错误')\n",
|
||
"# time.sleep(1)\n",
|
||
"\n",
|
||
"\n",
|
||
"# # 检测数据准确性, 需要检测放开\n",
|
||
"# # check_data(\"100028098|LISTING_PRICE\")\n",
|
||
"# # check_data(\"9137070016544622XB|DAY_Yield\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"运行中ing...\n",
|
||
"获取的token: eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJzdWIiOiJhcGlfZGV2IiwidGgiOiI4YTQ1NzdkYmQ5MTk2NzU3NThkNTc5OTlhMWU4OTFmZSIsImx0IjoiYXBpIiwiaXNzIjoiIiwidG0iOiJQQyIsImV4cCI6MTc0NDE5ODg0NywianRpIjoiZmJlMmI4MzA5NzFmNDBhMzhiZTA5YTZjMDEyZjU4YmQifQ.rGLp0UBfeu5JmoYXbGSgCpkrO2QnlAx8hFbbbDDXC8I\n",
|
||
"20250409\n",
|
||
" dataDate dataItemNo dataValue\n",
|
||
"0 2025-04-01 100028046|LISTING_PRICE 8208.0\n",
|
||
"1 2025-04-02 100028046|LISTING_PRICE 8244.0\n",
|
||
"2 2025-04-03 100028046|LISTING_PRICE 8244.0\n",
|
||
"3 2025-04-04 100028046|LISTING_PRICE 8165.0\n",
|
||
"4 2025-04-05 100028046|LISTING_PRICE 8114.0\n",
|
||
".. ... ... ...\n",
|
||
"183 2025-04-07 YHQMXBB|C01100008|STRIKE_PRICE 5180.0\n",
|
||
"184 2025-04-02 YHQMXBB|C01100008|STRIKE_PRICE 5310.0\n",
|
||
"185 2025-04-01 YHQMXBB|C01100008|STRIKE_PRICE 5260.0\n",
|
||
"186 2025-04-04 YHQMXBB|C01100008|STRIKE_PRICE 5230.0\n",
|
||
"187 2025-04-05 YHQMXBB|C01100008|STRIKE_PRICE 5180.0\n",
|
||
"\n",
|
||
"[188 rows x 3 columns]\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_9964\\3261286938.py:614: DeprecationWarning:\n",
|
||
"\n",
|
||
"The truth value of an empty array is ambiguous. Returning False, but in future this will result in an error. Use `array.size > 0` to check that an array is not empty.\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"当月数据更新完成\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_9964\\3261286938.py:255: UserWarning:\n",
|
||
"\n",
|
||
"The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n",
|
||
"\n",
|
||
"C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_9964\\3261286938.py:257: UserWarning:\n",
|
||
"\n",
|
||
"The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Using matplotlib backend: QtAgg\n",
|
||
"%pylab is deprecated, use %matplotlib inline and import the required libraries.\n",
|
||
"Populating the interactive namespace from numpy and matplotlib\n",
|
||
"Fitting 3 folds for each of 180 candidates, totalling 540 fits\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"d:\\ProgramData\\anaconda3\\Lib\\site-packages\\IPython\\core\\magics\\pylab.py:162: UserWarning:\n",
|
||
"\n",
|
||
"pylab import has clobbered these variables: ['plot', 'random', '__version__', 'datetime']\n",
|
||
"`%matplotlib` prevents importing * from pylab and numpy\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Date\n",
|
||
"2025-04-09 5179.792969\n",
|
||
"Name: 日度预测价格, dtype: float32\n",
|
||
"预测值： 5179.79\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_9964\\3261286938.py:203: UserWarning:\n",
|
||
"\n",
|
||
"The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n",
|
||
"\n",
|
||
"C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_9964\\3261286938.py:205: UserWarning:\n",
|
||
"\n",
|
||
"The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.\n",
|
||
"\n",
|
||
"C:\\Users\\EDY\\AppData\\Local\\Temp\\ipykernel_9964\\3261286938.py:237: FutureWarning:\n",
|
||
"\n",
|
||
"Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n",
|
||
"\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"\n",
|
||
"if __name__ == \"__main__\":\n",
|
||
" print(\"运行中ing...\")\n",
|
||
" # 每天定时12点运行\n",
|
||
" # while True:\n",
|
||
" # # 获取当前时间\n",
|
||
" # current_time = time.strftime(\"%H:%M:%S\", time.localtime())\n",
|
||
" # try:\n",
|
||
" # # 判断当前时间是否为执行任务的时间点\n",
|
||
" # if current_time == \"12:00:00\":\n",
|
||
" # print(\"执行定时任务\")\n",
|
||
" # main()\n",
|
||
" # elif current_time == \"20:00:00\":\n",
|
||
" # start_1()\n",
|
||
" # time.sleep(1)\n",
|
||
" # except:\n",
|
||
" # print(f\"{current_time}执行失败\")\n",
|
||
"\n",
|
||
" # 检测数据准确性, 需要检测放开\n",
|
||
" # check_data(\"100028098|LISTING_PRICE\")\n",
|
||
" # check_data(\"9137070016544622XB|DAY_Yield\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# start_date = datetime(2025, 4, 2)\n",
|
||
"# end_date = datetime(2025, 4, 3)\n",
|
||
"# token = get_head_auth()\n",
|
||
"\n",
|
||
"# while start_date < end_date:\n",
|
||
"# date = start_date.strftime('%Y%m%d')\n",
|
||
"# date2 = start_date.strftime('%Y-%m-%d')\n",
|
||
"# queryDataListItemNos(date=start_date,token=token)\n",
|
||
"# updateYesterdayExcelData(date=date2,token=token)\n",
|
||
"# start(date)\n",
|
||
"# # # time.sleep(1)\n",
|
||
"# # start_1(start_date)\n",
|
||
"# start_date += timedelta(days=1)\n",
|
||
"# time.sleep(5)\n",
|
||
"\n",
|
||
"# # print(price_list)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "base",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.11.7"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 4
|
||
}
|